{
  "slug": "webmcp-for-site-owners",
  "title": "How to Add WebMCP Tools to Your Website",
  "description": "How a site owner adds WebMCP tools as of 19 November 2026: origin trial tokens, the testing flag, document.modelContext.registerTool, annotations, the Permissions Policy tools feature, security risks, feature detection and which flows to expose.",
  "kind": "sub",
  "order": 8,
  "target_query": "how to add WebMCP tools to your website",
  "secondary_queries": [],
  "tags": [
    "webmcp",
    "origin-trial",
    "permissions-policy",
    "browser-agents",
    "chrome",
    "edge",
    "prompt-injection"
  ],
  "published": "2026-11-19",
  "updated": "2026-11-19",
  "words": 1607,
  "estimated_tokens": 2137,
  "premium": false,
  "rights": {
    "access": "free",
    "note": "Editorial guides are always free and never part of the licensed corpus.",
    "license": "https://changegamer.ai/license.xml",
    "pricing": "https://changegamer.ai/api/pricing.json",
    "payment": "https://changegamer.ai/api/payment.json"
  },
  "license": "https://changegamer.ai/license.xml",
  "citation": "ChangeGamer (2026-11-19). How to Add WebMCP Tools to Your Website. ChangeGamer. https://changegamer.ai/articles/webmcp-for-site-owners (updated 2026-11-19).",
  "bibtex": "@misc{changegamer_webmcp_for_site_owners, title = {How to Add WebMCP Tools to Your Website}, publisher = {ChangeGamer}, year = {2026}, url = {https://changegamer.ai/articles/webmcp-for-site-owners}, note = {Updated 2026-11-19}}",
  "canonical": "https://changegamer.ai/articles/webmcp-for-site-owners",
  "markdown": "https://changegamer.ai/articles/webmcp-for-site-owners.md",
  "takeaways": [
    "WebMCP lets a page register JavaScript tools through document.modelContext.registerTool(tool, options), but as of 19 November 2026 the specification is a Draft Community Group Report, not a W3C Standard.",
    "blink-dev approved a WebMCP experiment for M149 to M156 inclusive on 18 May 2026 and the Chrome origin trial opened in Chrome 149, while Edge lists its trial with an expiry of 30 March 2027, so production use means trial tokens, not general availability.",
    "A WebMCP tool is unregistered by aborting the AbortSignal passed in registerTool options, because the specification defines no unregisterTool method.",
    "A site can switch WebMCP off for a document and its frames with the response header Permissions-Policy: tools=(), which the specification says is enforced before page scripts run.",
    "The WebMCP specification warns that nothing guarantees a tool's declared intent matches its behaviour, so a site should make each description match exactly what execute does."
  ],
  "outline": [
    {
      "depth": 2,
      "text": "Which browsers can run WebMCP tools today?",
      "anchor": "which-browsers-can-run-webmcp-tools-today",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#which-browsers-can-run-webmcp-tools-today"
    },
    {
      "depth": 2,
      "text": "How do you enable the origin trial and the local flag?",
      "anchor": "how-do-you-enable-the-origin-trial-and-the-local-flag",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#how-do-you-enable-the-origin-trial-and-the-local-flag"
    },
    {
      "depth": 2,
      "text": "How do you register a tool with registerTool?",
      "anchor": "how-do-you-register-a-tool-with-registertool",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#how-do-you-register-a-tool-with-registertool"
    },
    {
      "depth": 2,
      "text": "How do you remove a tool again?",
      "anchor": "how-do-you-remove-a-tool-again",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#how-do-you-remove-a-tool-again"
    },
    {
      "depth": 2,
      "text": "What do the annotations do?",
      "anchor": "what-do-the-annotations-do",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#what-do-the-annotations-do"
    },
    {
      "depth": 2,
      "text": "Which Permissions Policy setting controls WebMCP?",
      "anchor": "which-permissions-policy-setting-controls-webmcp",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#which-permissions-policy-setting-controls-webmcp"
    },
    {
      "depth": 2,
      "text": "What can go wrong when you expose tools?",
      "anchor": "what-can-go-wrong-when-you-expose-tools",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#what-can-go-wrong-when-you-expose-tools"
    },
    {
      "depth": 2,
      "text": "How should you feature-detect and fall back?",
      "anchor": "how-should-you-feature-detect-and-fall-back",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#how-should-you-feature-detect-and-fall-back"
    },
    {
      "depth": 2,
      "text": "Which flows should you expose first?",
      "anchor": "which-flows-should-you-expose-first",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#which-flows-should-you-expose-first"
    },
    {
      "depth": 2,
      "text": "Does ChangeGamer register WebMCP tools?",
      "anchor": "does-changegamer-register-webmcp-tools",
      "url": "https://changegamer.ai/articles/webmcp-for-site-owners#does-changegamer-register-webmcp-tools"
    }
  ],
  "faq": [
    {
      "question": "Does WebMCP work in Firefox or Safari?",
      "answer": "No status exists for either as of 19 November 2026. The WebMCP implementation-status page lists only a standards-position thread for Firefox (mozilla/standards-positions#1412) and one for Safari (WebKit/standards-positions#670), so a site must treat both as having no support."
    },
    {
      "question": "Is the HTML form-based declarative WebMCP API available?",
      "answer": "Not as part of the specification. The WebMCP README (fetched 19 November 2026) says a declarative form-based API is being explored and is not part of the specification at this time. A separate explainer proposes attributes such as toolname and tooldescription, but its schema algorithms are marked TBD."
    },
    {
      "question": "Does a WebMCP tool need HTTPS?",
      "answer": "Yes. The WebMCP interface is marked [SecureContext] in the draft specification of 13 November 2026, so document.modelContext exists only on HTTPS pages and plain HTTP pages must fall back to ordinary interaction."
    },
    {
      "question": "Can a WebMCP tool run without a user watching?",
      "answer": "Partly. The WebMCP README lists human-in-the-loop workflows as the goal but says tools can also be used for task completion in headless scenarios; fully autonomous workflows with no browser UI are a non-goal, and the README says user prompting and elicitation is an open question that has not been designed yet."
    }
  ],
  "body": "A site owner adds WebMCP tools by calling `document.modelContext.registerTool()` from page JavaScript, on an HTTPS page, in a browser that has the feature enabled. As of 19 November 2026 that means an origin trial or a local flag, because the specification is a Draft Community Group Report from the W3C Web Machine Learning Community Group, not a W3C Standard. The [pillar](/articles/agentic-browsing-in-production) frames whether a pilot is worth it, and the [WebMCP reference](/resources/webmcp) holds the contract. This article is the sequence: how to turn it on, what to register, what to lock down and what not to expose.\n\n## Which browsers can run WebMCP tools today?\n\nAmong browsers, only Chrome and Edge run WebMCP as of 19 November 2026, both through origin trials (an opt-in mechanism, so by our reading neither turns it on by default); ChatGPT Desktop is a listed agent client, not a browser. The table uses the WebMCP implementation-status page and the vendor pages, all read on that date.\n\n| Client | State on 19 November 2026 | Source |\n|---|---|---|\n| Chrome | Origin trial opened in Chrome 149; blink-dev approved an experiment for \"M149 to M156 inclusive\" on 18 May 2026 | blink-dev intent, Chrome blog of 9 June 2026 |\n| Edge | Origin trial live in Edge 150; trial listed with expiry 30 March 2027 | Edge origin-trial page, implementation-status |\n| Brave | Leo AI chat support listed for Brave 1.102.2, expected 5 January 2027, so not in a stable release yet | implementation-status, brave-browser#55232 |\n| ChatGPT Desktop | Listed as \"Supported\"; an agent client, not a browser | implementation-status |\n| Firefox, Safari | No status; standards-position threads only | mozilla/standards-positions#1412, WebKit/standards-positions#670 |\n\nNo primary source we read confirms a general-availability milestone for Chrome, so do not plan a launch date around one. The older corpus entry of 9 September 2026 describes Brave as having experimental support; the implementation-status page now shows it as pending. For the wider product picture see [the agentic browsers reference](/resources/agentic-browsers).\n\n## How do you enable the origin trial and the local flag?\n\nSign up for each vendor's trial and serve that vendor's token on your pages (the general origin-trial mechanism, not a WebMCP-specific instruction), or enable the `about:flags#enable-webmcp-testing` flag for local development. The Chrome blog of 9 June 2026 says \"In Chrome 149, you can sign up for the WebMCP origin trial.\" The Edge trial page says the trial allows sites to register tools for use by agents hosted by the site or in Chrome.\n\nOrigin-trial tokens are per browser vendor, so a Chrome token does not enable Edge. That is the general origin-trial model as described in secondary guides, not a WebMCP-specific statement from a primary source. Budget for two registrations and two renewal dates. Trials expire, so a page must work when the token lapses.\n\n## How do you register a tool with registerTool?\n\nYou call `registerTool(tool, options)` with a tool object and an options object. The README (fetched 19 November 2026) says the tool has a `name`, a `description`, a JSON Schema `inputSchema` and an `execute` callback. The draft's `ModelContextTool` dictionary also lists `title`, `outputSchema` and `annotations`. The snippet is illustrative and uses only members from those sources; the tool and its endpoint are invented.\n\n```js\n// Illustrative only: names and the /api/stock endpoint are placeholders.\nif ('modelContext' in document) {\n  const controller = new AbortController();\n  try {\n    document.modelContext.registerTool(\n      {\n        name: 'check_stock',\n        title: 'Check stock',\n        description: 'Returns whether a product SKU is in stock. Does not change anything.',\n        inputSchema: {\n          type: 'object',\n          properties: { sku: { type: 'string' } },\n          required: ['sku'],\n        },\n        annotations: { readOnlyHint: true },\n        execute: async ({ sku }) => {\n          const res = await fetch('/api/stock?sku=' + encodeURIComponent(sku));\n          return await res.json();\n        },\n      },\n      { signal: controller.signal },\n    ).catch(() => {\n      // registerTool returns a promise that rejects (NotAllowedError) if a Permissions Policy blocks the feature; keep the normal UI.\n    });\n  } catch (err) {\n    // Synchronous errors, for example a malformed tool object; keep the normal UI.\n  }\n}\n```\n\nThe options also take `exposedTo`, a list of cross-origin origins the tool is shared with; the README documents that member, so confirm it against the current draft before relying on it. The README also documents `getTools()`, `executeTool()` and a `toolchange` event.\n\n## How do you remove a tool again?\n\nYou abort the `signal` you passed in the options, because there is no `unregisterTool` method. The 13 November 2026 draft defines `registerTool`, `getTools` and `executeTool` only. In the snippet above, `controller.abort()` removes `check_stock`. Tie that call to the state that makes a tool valid, for example sign-out or leaving a checkout step, so an agent never sees a tool the page can no longer honour.\n\n## What do the annotations do?\n\nThe annotations are hints to the agent client, not enforcement. The draft's `ToolAnnotations` list `readOnlyHint`, `untrustedContentHint`, `consequentialHint` and `debugging`. Section 6.4.4 says `untrustedContentHint` signals that a payload requires heightened security handling; output that includes user-generated content is one example. Section 6.4.5 says `consequentialHint` signals a consequential action so agents can require user confirmation, for example before a money transfer.\n\nSet them honestly, because a client that ignores them gives you no protection. Whether a given agent honours them is a property of that client, and we found no published list.\n\n## Which Permissions Policy setting controls WebMCP?\n\nThe Permissions Policy feature `tools` controls it, with a default allowlist of `'self'`. It gates `registerTool()`, `getTools()` and `executeTool()`. A cross-origin iframe needs `allow=\"tools\"` on its frame element before its scripts can register tools. To opt out entirely, section 6.4.1 says to deliver the header below, which makes the feature unavailable to the document and its descendant frames before page scripts run, including injected or compromised scripts.\n\n```http\n# Response header value to add in your own server or CDN config (illustrative)\nPermissions-Policy: tools=()\n```\n\nTo confirm it on your own domain, request a page with `curl -sI` and look for that header.\n\nPair this with the other site-side mechanism, [Web Bot Auth](/articles/web-bot-auth-for-browser-agents): signing says who is calling, while WebMCP says what a page offers (our inference).\n\n## What can go wrong when you expose tools?\n\nFour risks follow from the draft's section 6.3, and exposure makes each one your site's problem. The prompt-injection mechanics are in [prompt injection against browser agents](/articles/prompt-injection-against-browser-agents), and the checklists are in the [agentic security checklist](/resources/agentic-security-checklist) and [prompt injection design patterns](/resources/prompt-injection-design-patterns).\n\n- **Tool poisoning.** Hostile text in tool metadata, such as a description written by a third party, steers the agent.\n- **Output injection.** Return values that include user-generated content, such as reviews, can carry instructions. That is the case `untrustedContentHint` exists for.\n- **Implementation as target.** The agent's path through a tool may be validated differently from the UI path, so an input you would block in a form may pass through `execute`.\n- **Misrepresented intent.** Section 6.3.2 says \"There is no guarantee that a WebMCP tool's declared intent matches its actual behavior.\" Its example is a tool described as \"finalizing\" a cart that actually completes a purchase.\n\nSection 6.4.2 gives tool names a nominal 128-character limit and says other input limits are still under evaluation (Issue #73). It says the name restriction \"would not fully solve prompt injection attacks\". Validate every argument server-side as you would any public endpoint.\n\n## How should you feature-detect and fall back?\n\nCheck for `document.modelContext` before registering and make the page fully usable without it. The check in the snippet above does that: when the property is missing (on an unsupported browser, or on plain HTTP because the interface is [SecureContext]), nothing is registered. If the feature is disabled by `tools=()` or a trial token has lapsed, registration may fail instead: the promise `registerTool()` returns rejects, which is why the call has a `.catch()` (and sits in a try/catch for synchronous errors) and the normal UI remains. Do not branch your layout on it.\n\nDo not rely on the declarative route. The README says a form-based API is being explored, and the explainer (fetched 19 November 2026) proposes attributes (`toolname`, `tooldescription`, `toolautosubmit`, `toolparamdescription`) while marking its schema algorithms \"TBD\". It says \"Chromium is implementing a loose version of this\", so treat it as a prototype. Note that `toolautosubmit` would let an agent submit without the user checking first.\n\n## Which flows should you expose first?\n\nExpose read-only flows first, such as search, availability and order status, then add consequential ones only behind explicit confirmation. This is ChangeGamer's inference, not a published recommendation. Read-only tools carry a `readOnlyHint` and do the least damage if misused, and a tool that changes state should carry `consequentialHint`, so a client can ask the person first. Leave out flows where the cost of a wrong call is large and you cannot verify the caller. The README treats confirmation prompting as an open design question, so do not assume the client will do it for you.\n\n## Does ChangeGamer register WebMCP tools?\n\nChangeGamer registers none, as verified in the repository on 19 November 2026. The string `modelContext` appears only in content files, with no registration in `worker/` or `public/`. Its `_headers` file sends `Permissions-Policy: geolocation=(), camera=(), microphone=(), browsing-topics=()` and omits `tools`, so the `'self'` default applies.\n\nChangeGamer's backlog deferred WebMCP on 16 September 2026 as \"not-yet-honest\", with one precondition: someone must decide that shipping browser-side tools justifies the extra JavaScript, given that the site's own position is that agents should consume its Markdown and JSON variants instead of driving the DOM. Some third-party guides report that the API moved from `navigator.modelContext` to `document.modelContext` in mid-2026; that is a secondary report only, but it shows how quickly API naming goes stale in a draft.\n",
  "cluster": {
    "id": "browser-agents-in-production",
    "title": "Browser agents and agentic browsing in production",
    "description": "How to build, run and prepare for browser-driving agents — the computer-use loop, accessibility-tree vs screenshot grounding, cost and latency, page-borne prompt injection, logged-in-session risk, remote browsers and anti-bot, Web Bot Auth request signing, WebMCP for site owners, evaluation and the product landscape — not crawler and retrieval readiness (agent-ready-web) and not generic prompt-injection defense (agent-security-operations).",
    "status": "active",
    "pillar": {
      "slug": "agentic-browsing-in-production",
      "title": "Agentic Browsing in Production: Building, Securing and Preparing for Browser Agents",
      "description": "An operator guide to agentic browsing: the computer-use loop, accessibility-tree vs screenshot harnesses, cost and latency, page-borne prompt injection, logged-in-session risk, Web Bot Auth, WebMCP for site owners, evaluation and a launch sequence.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/agentic-browsing-in-production",
      "markdown": "https://changegamer.ai/articles/agentic-browsing-in-production.md",
      "json": "https://changegamer.ai/api/articles/agentic-browsing-in-production.json"
    },
    "articles": [
      {
        "slug": "computer-use-api-loop",
        "title": "Computer Use API: How the Screenshot-Action Loop Works Across Anthropic, OpenAI and Google",
        "description": "How the vendor computer use API loop works: screenshot in, structured action out, harness executes, new screenshot back. Tool names, coordinate systems, step caps, confirmation gates and what to log, for Anthropic, OpenAI and Google.",
        "kind": "sub",
        "order": 1,
        "html": "https://changegamer.ai/articles/computer-use-api-loop",
        "markdown": "https://changegamer.ai/articles/computer-use-api-loop.md",
        "json": "https://changegamer.ai/api/articles/computer-use-api-loop.json"
      },
      {
        "slug": "browser-agent-harness-comparison",
        "title": "browser-use vs Playwright MCP vs Stagehand: Which Open Browser Harness to Pick",
        "description": "browser-use vs Playwright MCP vs Stagehand compared as of 13 November 2026: how each exposes the browser to the model, grounding, language, session handling, the security caveats the READMEs state, hosted options and a decision table.",
        "kind": "sub",
        "order": 2,
        "html": "https://changegamer.ai/articles/browser-agent-harness-comparison",
        "markdown": "https://changegamer.ai/articles/browser-agent-harness-comparison.md",
        "json": "https://changegamer.ai/api/articles/browser-agent-harness-comparison.json"
      },
      {
        "slug": "browser-agent-cost-and-latency",
        "title": "Browser Agent Cost per Task: A Formula, the Levers and the Latency Caveat",
        "description": "How to compute browser agent cost per task as of 14 November 2026: a formula for screenshots and toolset overhead, an illustrative worked example, Anthropic image-token sizes, the cost levers and why the vendor pages read on 14 November 2026 give no latency figure.",
        "kind": "sub",
        "order": 3,
        "html": "https://changegamer.ai/articles/browser-agent-cost-and-latency",
        "markdown": "https://changegamer.ai/articles/browser-agent-cost-and-latency.md",
        "json": "https://changegamer.ai/api/articles/browser-agent-cost-and-latency.json"
      },
      {
        "slug": "prompt-injection-against-browser-agents",
        "title": "Prompt Injection in AI Browser Agents: Five Vectors and the Controls Vendors Document",
        "description": "ChangeGamer's grouping of the browser-specific prompt injection vectors as of 15 November 2026 (hidden page text, user-generated content, CometJacking URLs, screenshot text, seeded inbox emails) and which vendor-documented control addresses each, with a vector-to-control table.",
        "kind": "sub",
        "order": 4,
        "html": "https://changegamer.ai/articles/prompt-injection-against-browser-agents",
        "markdown": "https://changegamer.ai/articles/prompt-injection-against-browser-agents.md",
        "json": "https://changegamer.ai/api/articles/prompt-injection-against-browser-agents.json"
      },
      {
        "slug": "logged-in-sessions-and-blast-radius",
        "title": "How to Isolate a Browser Agent From a Logged-In Session",
        "description": "How to choose where a browser agent's session state comes from as of 16 November 2026 (your real profile, a persistent agent profile, a fresh profile, an injected Playwright storageState file, or a scoped API credential) and how to bound what it can reach.",
        "kind": "sub",
        "order": 5,
        "html": "https://changegamer.ai/articles/logged-in-sessions-and-blast-radius",
        "markdown": "https://changegamer.ai/articles/logged-in-sessions-and-blast-radius.md",
        "json": "https://changegamer.ai/api/articles/logged-in-sessions-and-blast-radius.json"
      },
      {
        "slug": "remote-browsers-and-anti-bot",
        "title": "Headless Browser for AI Agents: Local, Remote or Managed?",
        "description": "How to choose between a local headless browser and a managed remote browser (Browserbase, Bright Data, Cloudflare Browser Run) or self-hosted Crawlee as of 17 November 2026, how agents connect over CDP, and where anti-bot handling stops.",
        "kind": "sub",
        "order": 6,
        "html": "https://changegamer.ai/articles/remote-browsers-and-anti-bot",
        "markdown": "https://changegamer.ai/articles/remote-browsers-and-anti-bot.md",
        "json": "https://changegamer.ai/api/articles/remote-browsers-and-anti-bot.json"
      },
      {
        "slug": "web-bot-auth-for-browser-agents",
        "title": "How to Sign Browser Agent Requests With Web Bot Auth",
        "description": "How a team running a browser agent signs its outbound requests with Web Bot Auth as of 18 November 2026: Ed25519 key, signed key directory, the three headers, the Signature-Agent divergence, Cloudflare Verified status and key rotation.",
        "kind": "sub",
        "order": 7,
        "html": "https://changegamer.ai/articles/web-bot-auth-for-browser-agents",
        "markdown": "https://changegamer.ai/articles/web-bot-auth-for-browser-agents.md",
        "json": "https://changegamer.ai/api/articles/web-bot-auth-for-browser-agents.json"
      },
      {
        "slug": "webmcp-for-site-owners",
        "title": "How to Add WebMCP Tools to Your Website",
        "description": "How a site owner adds WebMCP tools as of 19 November 2026: origin trial tokens, the testing flag, document.modelContext.registerTool, annotations, the Permissions Policy tools feature, security risks, feature detection and which flows to expose.",
        "kind": "sub",
        "order": 8,
        "html": "https://changegamer.ai/articles/webmcp-for-site-owners",
        "markdown": "https://changegamer.ai/articles/webmcp-for-site-owners.md",
        "json": "https://changegamer.ai/api/articles/webmcp-for-site-owners.json"
      },
      {
        "slug": "evaluating-browser-agents",
        "title": "OSWorld vs WebArena: Which Benchmark Tells You Anything About Your Browser Agent?",
        "description": "OSWorld vs WebArena as read on 20 November 2026: what OSWorld, OSWorld-Verified, OSWorld 2.0, WebArena, VisualWebArena and Online-Mind2Web each measure, how they are scored, what running them involves and what none of them covers.",
        "kind": "sub",
        "order": 9,
        "html": "https://changegamer.ai/articles/evaluating-browser-agents",
        "markdown": "https://changegamer.ai/articles/evaluating-browser-agents.md",
        "json": "https://changegamer.ai/api/articles/evaluating-browser-agents.json"
      }
    ]
  },
  "navigation": {
    "pillar": {
      "slug": "agentic-browsing-in-production",
      "title": "Agentic Browsing in Production: Building, Securing and Preparing for Browser Agents",
      "description": "An operator guide to agentic browsing: the computer-use loop, accessibility-tree vs screenshot harnesses, cost and latency, page-borne prompt injection, logged-in-session risk, Web Bot Auth, WebMCP for site owners, evaluation and a launch sequence.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/agentic-browsing-in-production",
      "markdown": "https://changegamer.ai/articles/agentic-browsing-in-production.md",
      "json": "https://changegamer.ai/api/articles/agentic-browsing-in-production.json"
    },
    "previous": {
      "slug": "web-bot-auth-for-browser-agents",
      "title": "How to Sign Browser Agent Requests With Web Bot Auth",
      "description": "How a team running a browser agent signs its outbound requests with Web Bot Auth as of 18 November 2026: Ed25519 key, signed key directory, the three headers, the Signature-Agent divergence, Cloudflare Verified status and key rotation.",
      "kind": "sub",
      "order": 7,
      "html": "https://changegamer.ai/articles/web-bot-auth-for-browser-agents",
      "markdown": "https://changegamer.ai/articles/web-bot-auth-for-browser-agents.md",
      "json": "https://changegamer.ai/api/articles/web-bot-auth-for-browser-agents.json"
    },
    "next": {
      "slug": "evaluating-browser-agents",
      "title": "OSWorld vs WebArena: Which Benchmark Tells You Anything About Your Browser Agent?",
      "description": "OSWorld vs WebArena as read on 20 November 2026: what OSWorld, OSWorld-Verified, OSWorld 2.0, WebArena, VisualWebArena and Online-Mind2Web each measure, how they are scored, what running them involves and what none of them covers.",
      "kind": "sub",
      "order": 9,
      "html": "https://changegamer.ai/articles/evaluating-browser-agents",
      "markdown": "https://changegamer.ai/articles/evaluating-browser-agents.md",
      "json": "https://changegamer.ai/api/articles/evaluating-browser-agents.json"
    }
  },
  "resources": [
    {
      "slug": "webmcp",
      "html": "https://changegamer.ai/resources/webmcp",
      "markdown": "https://changegamer.ai/resources/webmcp.md",
      "json": "https://changegamer.ai/api/resources/webmcp.json"
    },
    {
      "slug": "agentic-security-checklist",
      "html": "https://changegamer.ai/resources/agentic-security-checklist",
      "markdown": "https://changegamer.ai/resources/agentic-security-checklist.md",
      "json": "https://changegamer.ai/api/resources/agentic-security-checklist.json"
    },
    {
      "slug": "prompt-injection-design-patterns",
      "html": "https://changegamer.ai/resources/prompt-injection-design-patterns",
      "markdown": "https://changegamer.ai/resources/prompt-injection-design-patterns.md",
      "json": "https://changegamer.ai/api/resources/prompt-injection-design-patterns.json"
    },
    {
      "slug": "agentic-browsers",
      "html": "https://changegamer.ai/resources/agentic-browsers",
      "markdown": "https://changegamer.ai/resources/agentic-browsers.md",
      "json": "https://changegamer.ai/api/resources/agentic-browsers.json"
    }
  ]
}